seed slicevLLM v0.23.0evidence: source code and documentation
Coverage
Coverage for a small vLLM v0.23.0 metric slice that exposes scheduler queue state, KV cache usage, and preemption signals.
Strong for whether the selected v0.23.0 metrics exist and what source fields they observe; weak for alert thresholds and workload-specific interpretation.
This topic is intentionally scoped to selected Prometheus metrics that connect to the existing scheduler/KV pressure graph; it is not a full vLLM observability catalog.
Claims in this topic (8)
| Claim | Verified |
|---|
In vLLM v0.23.0, vllm:num_requests_running is a Prometheus gauge for the number of requests in model execution batches. | 4 hr ago |
In vLLM v0.23.0, vllm:num_requests_running is set from SchedulerStats.num_running_reqs and observes scheduler running-request state. | 4 hr ago |
In vLLM v0.23.0, vllm:num_requests_waiting is a Prometheus gauge for the number of requests waiting to be processed. | 4 hr ago |
In vLLM v0.23.0, vllm:num_requests_waiting_by_reason is a Prometheus gauge with reason labels capacity and deferred, and its reasons sum to vllm:num_requests_waiting. | 4 hr ago |
In vLLM v0.23.0, vllm:kv_cache_usage_perc is a Prometheus gauge for KV-cache usage where 1 means 100 percent usage. | 4 hr ago |
In vLLM v0.23.0, vllm:kv_cache_usage_perc is set from SchedulerStats.kv_cache_usage and observes KV-cache usage pressure. | 4 hr ago |
In vLLM v0.23.0, vllm:num_preemptions is a Prometheus counter for cumulative preemptions from the engine. | 4 hr ago |
In vLLM v0.23.0, vllm:num_preemptions increments from IterationStats.num_preempted_reqs, which is increased when engine-core events mark requests as preempted. | 4 hr ago |
Metrics in this topic (5)
Known gaps
The corpus does not include alert thresholds, benchmark baselines, or workload-specific healthy ranges for these metrics.
Schema.ai can identify and explain the metrics but should not yet recommend numeric alert thresholds.
Check: Add runtime evals, design-partner telemetry, or benchmark evidence before serving threshold guidance.
Availability records now inventory the complete fixed-name v0.23.0 PrometheusStatLogger metric surface, but semantic claims cover only the selected scheduler/KV pressure metrics.
Schema.ai can answer whether a fixed-name metric exists at v0.23.0 from the complete inventory, but interpretation claims remain limited to the seed slice.
Check: Promote semantic claims for additional inventoried metrics as they become eval-covered.
KV connector per-connector Prometheus metrics and vllm.stat_loggers plugin metrics are open extension points that register dynamic metric names not covered by the fixed-name inventory.
Absence answers must be scoped to first-party fixed-name registrations; a deployment with connector or plugin metrics can expose additional names.
Check: Record deployment-specific connector/plugin context as agent-supplied bindings, not corpus facts.
Schema.ai